[pt] A oferta de serviços por meio de interfaces conversacionais, ou chatbots, tem se tornado cada vez mais popular, com aplicações que variam de aplicativos de bancos e reserva de bilheteria a consultas em um banco de dados. No entanto, dado a quantidade massiva de dados disponível em alguns domínios, o usuário pode ter dificuldade em formular as consultas e recuperar as informações desejadas. Esta dissertação tem como objetivo investigar e avaliar o uso de recomendações na busca de informações numa base de dados de filmes através de chatbots. Neste trabalho, implementamos um chatbot por meio do uso de frameworks e técnicas da área de processamento de linguagem natural (NLP - Natural Language Processing). Para o reconhecimento de entidades e intenções, utilizamos o framework RASA NLU. Para a identificação das relações entre essas entidades, utilizamos as redes Transformers. Além disso, propomos diferentes estratégias para recomendações feitas a partir da ontologia de domínio. Para avaliação deste trabalho, conduzimos um estudo com usuários para avaliar o impacto das recomendações no uso do chatbot e aceitação da tecnologia por meio de um questionário baseado no Technology Acceptance Model (TAM). Por fim, discutimos os resultados do estudo, suas limitações e oportunidades de futuras melhorias. / [en] The offer of services provided through conversational interfaces, or chatbots, has become increasingly popular, with applications that range from bank applications and ticket booking to database queries. However, given the massive amount of data available in some domains, the user may find it difficult to formulate queries and retrieve the desired information. This dissertation investigates and evaluates the use of the recommendations in the search for information on a movie database through a chatbot. In this work, we implement a chatbot with the use of frameworks and techniques from the area of natural language processing (NLP). For the recognition of entities and intents, we use the RASA NLU framework. For the identification of relations between those entities, we use the Transformers networks. In addition, we propose different strategies for the recommendation from the domain ontology. To evaluate this work, we have conducted an empirical study with volunteer users to assess the impact of the recommendations on chatbot use and the acceptance of the technology through a survey based on the Technology Acceptance Model (TAM). Lastly, we discuss the results of this study, its limitations, and avenues for future improvements.

Nowadays, the effective management of information is extremely important for all spheres of our lives and applications such as search engines and question answering systems help users to find the information that they need. However, even when assisted by these various applications, people sometimes struggle to find what they want. For example, when choosing a product customers can be confused by the need to consider many features before they can reach a decision. Interactive question answering (IQA) systems can help customers in this process, by answering questions about products and initiating a dialogue with the customers when their needs are not clearly defined. The focus of this thesis is how to design an interactive question answering system that will assist users in choosing a product they are looking for, in an optimal way, when a large number of similar products are available. Such an IQA system will be based on selecting a set of characteristics (also referred to as product features in this thesis), that describe the relevant product, and narrowing the search space. We believe that the order in which these characteristics are presented in terms of these IQA sessions is of high importance. Therefore, they need to be ranked in order to have a dialogue which selects the product in an efficient manner. The research question investigated in this thesis is whether product characteristics mentioned in user reviews are important for a person who is likely to purchase a product and can therefore be used when designing an IQA system. We focus our attention on products such as mobile phones; however, the proposed techniques can be adapted for other types of products if the data is available. Methods from natural language processing (NLP) fields such as coreference resolution, relation extraction and opinion mining are combined to produce various rankings of phone features. The research presented in this thesis employs two corpora which contain texts related to mobile phones specifically collected for this thesis: a corpus of Wikipedia articles about mobile phones and a corpus of mobile phone reviews published on the Epinions.com website. Parts of these corpora were manually annotated with coreference relations, mobile phone features and relations between mentions of the phone and its features. The annotation is used to develop a coreference resolution module as well as a machine learning-based relation extractor. Rule-based methods for identification of coreference chains describing the phone are designed and thoroughly evaluated against the annotated gold standard. Machine learning is used to find links between mentions of the phone (identified by coreference resolution) and phone features. It determines whether some phone feature belong to the phone mentioned in the same sentence or not. In order to find the best rankings, this thesis investigates several settings. One of the hypotheses tested here is that the relatively low results of the proposed baseline are caused by noise introduced by sentences which are not directly related to the phone and phone feature. To test this hypothesis, only sentences which contained mentions of the mobile phone and a phone feature linked to it were processed to produce rankings of the phones features. Selection of the relevant sentences is based on the results of coreference resolution and relation extraction. Another hypothesis is that opinionated sentences are a good source for ranking the phone features. In order to investigate this, a sentiment classification system is also employed to distinguish between features mentioned in positive and negative contexts. The detailed evaluation and error analysis of the methods proposed form an important part of this research and ensure that the results provided in this thesis are reliable.

Permission from the author to release this work as open access is pending. Please contact the ICS library if you would like to view this work.

Les systèmes de question-réponse renvoient une réponse précise à une question formulée en langue naturelle. Les systèmes de question-réponse actuels, ainsi que les campagnes d'évaluation les évaluant, font en général l'hypothèse qu'une seule réponse est attendue pour une question. Or nous avons constaté que, souvent, ce n'était pas le cas, surtout quand on cherche les réponses sur le Web et non dans une collection finie de documents.Nous nous sommes donc intéressés au traitement des questions attendant plusieurs réponses à travers un système de question-réponse sur le Web en français. Pour cela, nous avons développé le système Citron capable d'extraire des réponses multiples différentes à des questions factuelles en domaine ouvert, ainsi que de repérer et d'extraire le critère variant (date, lieu) source de la multiplicité des réponses. Nous avons montré grâce à notre étude de différents corpus que les réponses à de telles questions se trouvaient souvent dans des tableaux ou des listes mais que ces structures sont difficilement analysables automatiquement sans prétraitement. C'est pourquoi, nous avons également développé l'outil Kitten qui permet d'extraire le contenu des documents HTML sous forme de texte et aussi de repérer, analyser et formater ces structures. Enfin, nous avons réalisé deux expériences avec des utilisateurs. La première expérience évaluait Citron et les êtres humains sur la tâche d'extraction de réponse multiples : les résultats ont montré que Citron était plus rapide que les êtres humains et que l'écart entre la qualité des réponses de Citron et celle des utilisateurs était raisonnable. La seconde expérience a évalué la satisfaction des utilisateurs concernant la présentation de réponses multiples : les résultats ont montré que les utilisateurs préféraient la présentation de Citron agrégeant les réponses et y ajoutant un critère variant (lorsqu'il existe) par rapport à la présentation utilisée lors des campagnes d'évaluation. / Question answering systems find and extract a precise answer to a question in natural language. Both current question-answering systems and evaluation campaigns often assume that only one single answeris expected for a question. Our corpus studies show that this is rarely the case, specially when answers are extracted from the Web instead of a frozen collection of documents.We therefore focus on questions expecting multiple correct answers fromthe Web by developping the question-answering system Citron. Citron is dedicated to extracting multiple answers in open domain and identifying theshifting criteria (date, location) which is often the reason of this answer multiplicity Our corpus studies show that the answers of this kind of questions are often located in structures such as tables and lists which cannot be analysed without a suitable preprocessing. Consequently we developed the Kitten software which aims at extracting text information from HTML documents and also both identifying and formatting these structures.We finally evaluate Citron through two experiments involving users. Thefirst experiment evaluates both Citron and human beings on a multipleanswer extraction task: results show that Citron was faster than humans andthat the quality difference between answers extracted by Citron andhumans was reasonable. The second experiment evaluates user satisfaction regarding the presentation of multiple answers: results show that user shave a preference for Citron presentation aggregating answers and adding the shifting criteria (if it exists) over the presentation used by evaluation campaigns.

Nos ambientes médico e de saúde, especificamente no tratamento clínico do paciente, o papel da informação descrita nos prontuários médicos é registrar o estado de saúde do paciente e auxiliar os profissionais diretamente ligados ao tratamento. A investigação dessas informações de estado clínico em pesquisas científicas na área de biomedicina podem suportar o desenvolvimento de padrões de prevenção e tratamento de enfermidades. Porém, ler artigos científicos é uma tarefa que exige tempo e disposição, uma vez que realizar buscas por informações específicas não é uma tarefa simples e a área médica e de saúde está em constante atualização. Além disso, os profissionais desta área, em sua grande maioria, possuem uma rotina estressante, trabalhando em diversos empregos e atendendo muitos pacientes em um único dia. O objetivo deste projeto é o desenvolvimento de um Framework de Question Answering (QA) para suportar o desenvolvimento de sistemas de QA, que auxiliem profissionais da área da saúde na busca rápida por informações, especificamente, em epigenética e doenças crônicas. Durante o processo de construção do framework, estão sendo utilizados dois frameworks desenvolvidos anteriormente pelo grupo de pesquisa da mestranda: o SisViDAS e o FREDS, além de desenvolver os demais módulos de processamento de pergunta e de respostas. O QASF foi avaliado por meio de uma coleção de referências e medidas estatísticas de desempenho e os resultados apontam valores de precisão em torno de 0.7 quando a revocação era 0.3, para ambos o número de artigos recuperados e analisados eram 200. Levando em consideração que as perguntas inseridas no QASF são longas, com 70 termos por pergunta em média, e complexas, o QASF apresentou resultados satisfatórios. Este projeto pretende contribuir na diminuição do tempo gasto por profissionais da saúde na busca por informações de interesse, uma vez que sistemas de QA fornecem respostas diretas e precisas sobre uma pergunta feita pelo usuário / The medical record describes health conditions of patients helping experts to make decisions about the treatment. The biomedical scientific knowledge can improve the prevention and the treatment of diseases. However, the search for relevant knowledge may be a hard task because it is necessary time and the healthcare research is constantly updating. Many healthcare professionals have a stressful routine, because they work in different hospitals or medical offices, taking care many patients per day. The goal of this project is to design a Question Answering Framework to support faster and more precise searches for information in epigenetic, chronic disease and thyroid images. To develop the proposal, we are reusing two frameworks that have already developed: SisViDAS and FREDS. These two frameworks are being exploited to compose a document processing module. The other modules (question and answer processing) are being completely developed. The QASF was evaluated by a reference collection and performance measures. The results show 0.7 of precision and 0.3 of recall for two hundred articles retrieved. Considering that the questions inserted on the framework have an average of seventy terms, the QASF shows good results. This project intends to decrease search time once QA systems provide straight and precise answers in a process started by a user question in natural language

No description available.

International studies have shown the reading competence of Indonesian students to be relatively low compared to other countries. Considering the importance of reading comprehension, the current research has two aims. The first is to provide some insight into the identification of students’ difficulty with reading. The second is to investigate the implementation of innovative methods for teaching reading comprehension in the Indonesian educational context. Both studies were conducted in state upper grade primary schools in Urban Sub District BCL in Bandung, Indonesia. Study One profiled students’ reading performance. Five measurement instruments were developed, written in Indonesian language. The construction of mental models was also introduced. Two hundred and sixty five Grade Five students from eight schools were measured for their competence in decoding, prior knowledge, comprehension monitoring, construction of mental models, reading comprehension specifically related to a particular topic, and their general reading comprehension. The students’ reading performance profiles were very varied. They showed the importance of each component for the achievement of reading comprehension. The profiles also showed the ability for each component of reading comprehension to compensate each other’s function to enable the students to perform well in reading comprehension. The best-fit model for the data accounted for 47% of students’ performance in reading comprehension. Study Two compared instructional interventions, and examined the way each method worked in the Indonesian educational context. The three instructional intervention methods were Reciprocal Teaching (RT), Instruction prompting students to develop Mental Models (IMM), and Instruction in Question Answering (IQA). Participants were one hundred and twelve students in the Sixth Grade from three primary schools. There were three groups in each school. Group 1 received RT followed by IMM (RT-IMM), Group 2 received IMM followed by RT (IMM-RT), and Group 3 received IQA. Group 3 was considered as the control group, since IQA is the traditional method widely adopted in Indonesia. Instruction was separated into 2 phases. Each phase consisted of four sessions of 30 minutes each over a two-week period. The implementation of IMM-RT tended to improve general reading comprehension more than other methods (RT-IMM and IQA). Interestingly, individuals who had a low performance in the pre-test for construction of mental models, improved their performance in the construction of mental models following implementation of RT at the first phase. The results support a conclusion that the IMM-RT combination is potentially effective for the enhancement of students’ reading comprehension. However, further results showed that, in order to implement RT and IMM in a common state school classroom in Indonesia, the teacher’s ability to manage and organise the group becomes crucial. Study Three was designed to validate the IMM-RT instructional intervention for improving performances of students with reading comprehension inadequacies, by addressing the limitations found in Study Two. Result showed that IMM-RT had potential for improving students’ performance in reading comprehension. The findings of the current study provide some understanding of reading comprehension in an Indonesian educational context. Moreover, the findings will add to the repertoire of educators about issues that need to be considered in implementing innovative methods for enhancing Indonesian students’ reading comprehension.

International studies have shown the reading competence of Indonesian students to be relatively low compared to other countries. Considering the importance of reading comprehension, the current research has two aims. The first is to provide some insight into the identification of students’ difficulty with reading. The second is to investigate the implementation of innovative methods for teaching reading comprehension in the Indonesian educational context. Both studies were conducted in state upper grade primary schools in Urban Sub District BCL in Bandung, Indonesia. Study One profiled students’ reading performance. Five measurement instruments were developed, written in Indonesian language. The construction of mental models was also introduced. Two hundred and sixty five Grade Five students from eight schools were measured for their competence in decoding, prior knowledge, comprehension monitoring, construction of mental models, reading comprehension specifically related to a particular topic, and their general reading comprehension. The students’ reading performance profiles were very varied. They showed the importance of each component for the achievement of reading comprehension. The profiles also showed the ability for each component of reading comprehension to compensate each other’s function to enable the students to perform well in reading comprehension. The best-fit model for the data accounted for 47% of students’ performance in reading comprehension. Study Two compared instructional interventions, and examined the way each method worked in the Indonesian educational context. The three instructional intervention methods were Reciprocal Teaching (RT), Instruction prompting students to develop Mental Models (IMM), and Instruction in Question Answering (IQA). Participants were one hundred and twelve students in the Sixth Grade from three primary schools. There were three groups in each school. Group 1 received RT followed by IMM (RT-IMM), Group 2 received IMM followed by RT (IMM-RT), and Group 3 received IQA. Group 3 was considered as the control group, since IQA is the traditional method widely adopted in Indonesia. Instruction was separated into 2 phases. Each phase consisted of four sessions of 30 minutes each over a two-week period. The implementation of IMM-RT tended to improve general reading comprehension more than other methods (RT-IMM and IQA). Interestingly, individuals who had a low performance in the pre-test for construction of mental models, improved their performance in the construction of mental models following implementation of RT at the first phase. The results support a conclusion that the IMM-RT combination is potentially effective for the enhancement of students’ reading comprehension. However, further results showed that, in order to implement RT and IMM in a common state school classroom in Indonesia, the teacher’s ability to manage and organise the group becomes crucial. Study Three was designed to validate the IMM-RT instructional intervention for improving performances of students with reading comprehension inadequacies, by addressing the limitations found in Study Two. Result showed that IMM-RT had potential for improving students’ performance in reading comprehension. The findings of the current study provide some understanding of reading comprehension in an Indonesian educational context. Moreover, the findings will add to the repertoire of educators about issues that need to be considered in implementing innovative methods for enhancing Indonesian students’ reading comprehension.

International studies have shown the reading competence of Indonesian students to be relatively low compared to other countries. Considering the importance of reading comprehension, the current research has two aims. The first is to provide some insight into the identification of students’ difficulty with reading. The second is to investigate the implementation of innovative methods for teaching reading comprehension in the Indonesian educational context. Both studies were conducted in state upper grade primary schools in Urban Sub District BCL in Bandung, Indonesia. Study One profiled students’ reading performance. Five measurement instruments were developed, written in Indonesian language. The construction of mental models was also introduced. Two hundred and sixty five Grade Five students from eight schools were measured for their competence in decoding, prior knowledge, comprehension monitoring, construction of mental models, reading comprehension specifically related to a particular topic, and their general reading comprehension. The students’ reading performance profiles were very varied. They showed the importance of each component for the achievement of reading comprehension. The profiles also showed the ability for each component of reading comprehension to compensate each other’s function to enable the students to perform well in reading comprehension. The best-fit model for the data accounted for 47% of students’ performance in reading comprehension. Study Two compared instructional interventions, and examined the way each method worked in the Indonesian educational context. The three instructional intervention methods were Reciprocal Teaching (RT), Instruction prompting students to develop Mental Models (IMM), and Instruction in Question Answering (IQA). Participants were one hundred and twelve students in the Sixth Grade from three primary schools. There were three groups in each school. Group 1 received RT followed by IMM (RT-IMM), Group 2 received IMM followed by RT (IMM-RT), and Group 3 received IQA. Group 3 was considered as the control group, since IQA is the traditional method widely adopted in Indonesia. Instruction was separated into 2 phases. Each phase consisted of four sessions of 30 minutes each over a two-week period. The implementation of IMM-RT tended to improve general reading comprehension more than other methods (RT-IMM and IQA). Interestingly, individuals who had a low performance in the pre-test for construction of mental models, improved their performance in the construction of mental models following implementation of RT at the first phase. The results support a conclusion that the IMM-RT combination is potentially effective for the enhancement of students’ reading comprehension. However, further results showed that, in order to implement RT and IMM in a common state school classroom in Indonesia, the teacher’s ability to manage and organise the group becomes crucial. Study Three was designed to validate the IMM-RT instructional intervention for improving performances of students with reading comprehension inadequacies, by addressing the limitations found in Study Two. Result showed that IMM-RT had potential for improving students’ performance in reading comprehension. The findings of the current study provide some understanding of reading comprehension in an Indonesian educational context. Moreover, the findings will add to the repertoire of educators about issues that need to be considered in implementing innovative methods for enhancing Indonesian students’ reading comprehension.

The advent of Massive Open Online Courses (MOOCs) allows massive volume of registrants to enrol in these MOOCs. This research aims to offer MOOCs registrants with automatic content related feedback to fulfil their cognitive needs. A framework is proposed which consists of three modules which are the subject ontology learning module, the short text classification module, and the question answering module. Unlike previous research, to identify relevant concepts for ontology learning a regular expression parser approach is used. Also, the relevant concepts are extracted from unstructured documents. To build the concept hierarchy, a frequent pattern mining approach is used which is guided by a heuristic function to ensure that sibling concepts are at the same level in the hierarchy. As this process does not require specific lexical or syntactic information, it can be applied to any subject. To validate the approach, the resulting ontology is used in a question-answering system which analyses students' content-related questions and generates answers for them. Textbook end of chapter questions/answers are used to validate the question-answering system. The resulting ontology is compared vs. the use of Text2Onto for the question-answering system, and it achieved favourable results. Finally, different indexing approaches based on a subject's ontology are investigated when classifying short text in MOOCs forum discussion data; the investigated indexing approaches are: unigram-based, concept-based and hierarchical concept indexing. The experimental results show that the ontology-based feature indexing approaches outperform the unigram-based indexing approach. Experiments are done in binary classification and multiple labels classification settings . The results are consistent and show that hierarchical concept indexing outperforms both concept-based and unigram-based indexing. The BAGGING and random forests classifiers achieved the best result among the tested classifiers.